Repository navigation
fix(detection): drop registry paths from search_code_patterns output - #209
Open
rudycelekli wants to merge 1 commit into
Open
rudycelekli wants to merge 1 commit into
rudycelekli wants to merge 1 commit into
Conversation
search_code_patterns returned raw source registry entries, including `path` values such as source_codes/mcp_servers_1/..., so the reasoning agent could read the benign/vulnerable/environment dataset split from the directory name. list_mcp_servers and get_source_code already strip these hints. Return the same name/category/description/capabilities metadata as list_mcp_servers. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
|
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What type of PR is this? (check all applicable)
Related issue: N/A (found by reading the code; reproduced on
mainat 6b33dff)What changed?
Map entries to name/category/description/capabilities, same as list_mcp_servers.
Why?
Context_providers/source_code_analyzer_server.py search_code_patterns returns
filtered_servers(raw source_codes_registry.yaml entries) asavailable_servers, includingpath. All 26 vulnerable servers have paths undersource_codes/mcp_servers_1/(README: "Vulnerable tools (26 servers)"), so a reasoning-agent call to this tool (all tools of the server are reachable; no --allowedTools restriction) reveals the dataset label. The module's own design says "No pre-analysis or cheating metadata"; list_mcp_servers strips path, and get_source_code returns relative paths "so dataset directory names do not become classifier hints".How did you test it?
search_code_patterns('x')['available_servers']paths -> {'mcp_servers_0': 78, 'mcp_servers_1': 26, 'mcp_servers_2': 12}. New testtest_search_code_patterns_omits_registry_paths: main fails, branch passes (28 passed in that file).pytest tests/ -q-> 257 passed, 1 failed: test_kills_grandchild_process_holding_inherited_stdio (known load-flaky, untouched code; load average ~50; passed on immediate rerun).Potential risks
The change only affects the input described above; other paths go through the same code as before, and the component's existing tests pass.
AI assistance: Claude Code (model Claude Opus 5.5) found this bug, wrote the fix and test, and drafted this description; submitted by @rudycelekli.
🤖 Generated with Claude Code